PGR-Net: Prior-Guided ROI Reasoning Network for Brain Tumor MRI Segmentation

TL;DR

PGR-Net introduces a prior-guided, ROI-aware framework with hierarchical decision and Gaussian-spatial decay modules to improve brain tumor MRI segmentation accuracy and efficiency.

Contribution

It proposes a novel explicit ROI reasoning network that incorporates spatial priors and a hierarchical decision mechanism for better tumor localization.

Findings

Achieves Dice scores of 89.02%, 91.82%, and 89.67% on BraTS datasets.

Outperforms existing methods with only 8.64M parameters.

Demonstrates stable and accurate tumor segmentation across multiple datasets.

Abstract

Brain tumor MRI segmentation is essential for clinical diagnosis and treatment planning, enabling accurate lesion detection and radiotherapy target delineation. However, tumor lesions occupy only a small fraction of the volumetric space, resulting in severe spatial sparsity, while existing segmentation networks often overlook clinically observed spatial priors of tumor occurrence, leading to redundant feature computation over extensive background regions. To address this issue, we propose PGR-Net (Prior-Guided ROI Reasoning Network) - an explicit ROI-aware framework that incorporates a data-driven spatial prior set to capture the distribution and scale characteristics of tumor lesions, providing global guidance for more stable segmentation. Leveraging these priors, PGR-Net introduces a hierarchical Top-K ROI decision mechanism that progressively selects the most confident lesion candidate regions across encoder layers to improve localization precision. We further develop the WinGS-ROI (Windowed Gaussian-Spatial Decay ROI) module, which uses multi-window Gaussian templates with a spatial decay function to produce center-enhanced guidance maps, thus directing feature learning throughout the network. With these ROI features, a windowed RetNet backbone is adopted to enhance localization reliability. Experiments on BraTS-2019/2023 and MSD Task01 show that PGR-Net consistently outperforms existing approaches while using only 8.64M Params, achieving Dice scores of 89.02%, 91.82%, and 89.67% on the Whole Tumor region. Code is available at https://github.com/CNU-MedAI-Lab/PGR-Net.